Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    book club

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    1.19
    ра
    1.05
    ח
    0.82
    ro
    0.78
    что
    0.74
    ق
    0.74
    audit
    0.73
    рати
    0.73
    خدم
    0.73
    hel
    0.71
    POSITIVE LOGITS
     Gutierrez
    0.88
     vence
    0.88
    ська
    0.87
     acquies
    0.87
    টিল
    0.85
    其他
    0.84
     ziua
    0.84
     iż
    0.84
     executar
    0.82
    ました
    0.82
    Act Density 0.000%

    No Known Activations